GOSAFEOPT: Scalable safe exploration for global optimization of dynamical systems
OPEN ACCESS
Loading...
Author / Producer
Date
2023-07
Publication Type
Journal Article
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
Learning optimal control policies directly on physical systems is challenging. Even a single failure can lead to costly hardware damage. Most existing model-free learning methods that guarantee safety, i.e., no failures, during exploration are limited to local optima. This work proposes GOSAFEOPT as the first provably safe and optimal algorithm that can safely discover globally optimal policies for systems with high-dimensional state space. We demonstrate the superiority of GOSAFEOPT over competing model-free safe learning methods in simulation and hardware experiments on a robot arm.
Permanent link
Publication status
published
External links
Editor
Book title
Journal / series
Volume
320
Pages / Article No.
103922
Publisher
Elsevier
Event
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Model-free learning; Bayesian optimization; Safe learning
Organisational unit
03908 - Krause, Andreas / Krause, Andreas
Notes
Funding
815943 - Reliable Data-Driven Decision Making in Cyber-Physical Systems (EC)
180545 - NCCR Automation (phase I) (SNF)
180545 - NCCR Automation (phase I) (SNF)